update Danniel Code

Project/Solution-Coding-02-Data Mining Process.R

@@ -1,25 +1,104 @@
-# Load data
-house.df <- read.csv("WestRoxbury.csv")
-
-# Extract the row numbers
-house.rows <- row.names(house.df)
-
-# Partition the row numbers into 10 equal subsets
-set.seed(100)
-house.rows.list <- list()
-for(i in 1:10){
-  house.rows.list[[i]] <- sample(house.rows, length(house.rows) / (10 - i + 1))
-  house.rows <- setdiff(house.rows, house.rows.list[[i]])
-}
-
-# Partition the data into 10 equal subsets
-house.df.list <- list()
-for(i in 1:10){
-  house.df.list[[i]] <- house.df[house.rows.list[[i]],]
-}
-
-# Display the number of observations in each subset
-for(i in 1:10){
-  print(paste("Number of observations in subset", i,
-              "=", dim(house.df.list[[i]])[1]))
-}
+# Load necessary libraries
+library(forecast)
+library(ggplot2)
+library(gplots)
+library(reshape)
+library(GGally)
+library(MASS)
+library(naniar)
+library(psych)
+
+# Load dataset
+setwd('/home/anpham/Nextcloud/cpp/Data Mining/Project')
+telco.df <- read.csv("Telco-Customer-Churn.csv", stringsAsFactors = FALSE)
+
+# Display first few rows
+head(telco.df)
+
+# Check structure
+str(telco.df)
+
+# Summary statistics
+describe(telco.df)
+
+# Convert categorical variables to factors
+categorical_vars <- c("gender", "SeniorCitizen", "Partner", "Dependents", "PhoneService",
+                      "MultipleLines", "InternetService", "OnlineSecurity", "OnlineBackup",
+                      "DeviceProtection", "TechSupport", "StreamingTV", "StreamingMovies",
+                      "Contract", "PaperlessBilling", "PaymentMethod", "Churn")
+telco.df[categorical_vars] <- lapply(telco.df[categorical_vars], factor)
+
+# Convert TotalCharges to numeric and handle missing values
+telco.df$TotalCharges <- as.numeric(telco.df$TotalCharges)
+telco.df$TotalCharges[is.na(telco.df$TotalCharges)] <- 0
+
+# Create new feature: Average Monthly Spend
+telco.df$AvgMonthlySpend <- with(telco.df, ifelse(tenure > 0, TotalCharges / tenure, MonthlyCharges))
+
+# Categorize tenure into groups
+telco.df$TenureCategory <- cut(telco.df$tenure,
+                               breaks = c(-Inf, 12, 48, Inf),
+                               labels = c("Short-Term", "Mid-Term", "Long-Term"))
+
+# Check missing values
+sum(is.na(telco.df))
+colSums(is.na(telco.df))
+
+# Visualize missing values
+gg_miss_var(telco.df)
+
+# Boxplots to detect outliers
+ggplot(telco.df, aes(y = MonthlyCharges)) +
+  geom_boxplot(fill = "skyblue") +
+  ggtitle("Boxplot of Monthly Charges") +
+  theme_minimal()
+
+ggplot(telco.df, aes(y = TotalCharges)) +
+  geom_boxplot(fill = "lightcoral") +
+  ggtitle("Boxplot of Total Charges") +
+  theme_minimal()
+
+# Histogram for numeric variables
+hist(telco.df$TotalCharges, col = "blue", main = "Distribution of TotalCharges")
+hist(telco.df$MonthlyCharges, col = "lightblue", border = "black", main="Distribution of Monthly Charges")
+
+# Density plot
+plot(density(telco.df$MonthlyCharges, na.rm = TRUE), col = "red", main = "Density of MonthlyCharges")
+
+# Boxplot of Monthly Charges by Churn status
+boxplot(telco.df$MonthlyCharges ~ telco.df$Churn,
+        main = "Monthly Charges by Churn Status",
+        xlab = "Churn (Yes/No)",
+        ylab = "Monthly Charges",
+        col = c("red", "blue"))
+
+# Scatter plot of tenure vs Monthly Charges
+plot(telco.df$tenure, telco.df$MonthlyCharges,
+     xlab = "Tenure (Months)",
+     ylab = "Monthly Charges ($)",
+     main = "Tenure vs. Monthly Charges",
+     col = "blue", pch = 16)
+
+# Scatter plot of tenure vs churn with jitter
+ggplot(telco.df, aes(x = Churn, y = tenure, color = Churn)) +
+  geom_jitter(width = 0.2, alpha = 0.6) +
+  labs(title = "Tenure by Churn Status",
+       x = "Churn (Yes/No)",
+       y = "Tenure (Months)") +
+  theme_minimal()
+
+# Convert Tenure to years
+telco.df$TenureYears <- telco.df$tenure / 12
+
+# Ensure "DSL" is properly recognized in InternetService
+dsl_data <- subset(telco.df, InternetService == "DSL", select = c(TenureYears, MonthlyCharges))
+
+# Scatter plot for DSL customers
+ggplot(dsl_data, aes(x = TenureYears, y = MonthlyCharges)) +
+  geom_point(color = "blue", alpha = 0.6) +
+  labs(title = "Monthly Charges vs. Tenure (DSL Customers)",
+       x = "Tenure (Years)",
+       y = "Monthly Charges ($)") +
+  theme_minimal()
+
+